Among the various types of semantic concepts modeled, events pose the greatest challenge in terms of computational power needed to represent the event and accuracy that can be ach...
We advocate the use of Gaussian Process Dynamical Models (GPDMs) for learning human pose and motion priors for 3D people tracking. A GPDM provides a lowdimensional embedding of hu...
— This paper applies the modified Fisher Information Matrix (FIM) motion algorithm previously proposed by the authors to the task of locating a circular biochemical source. We d...
In motion-compensated wavelet based video coders (MCWT), it is known that a precise motion estimation is necessary to minimize the wavelet coefficients energy. However, a motion v...
We propose a Bayesian framework for representing and recognizing local image motion in terms of two primitive models: translation and motion discontinuity. Motion discontinuities ...